Image Classification
Transformers
PyTorch
TensorBoard
swin
Generated from Trainer
Eval Results (legacy)
Instructions to use autoevaluate/image-multi-class-classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use autoevaluate/image-multi-class-classification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="autoevaluate/image-multi-class-classification") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("autoevaluate/image-multi-class-classification") model = AutoModelForImageClassification.from_pretrained("autoevaluate/image-multi-class-classification") - Notebooks
- Google Colab
- Kaggle
File size: 391 Bytes
4371161 | 1 2 3 4 5 6 7 8 9 10 11 12 13 | {
"epoch": 1.0,
"eval_accuracy": 0.9833333333333333,
"eval_loss": 0.05558411777019501,
"eval_runtime": 38.4928,
"eval_samples_per_second": 155.873,
"eval_steps_per_second": 4.884,
"total_flos": 1.342523444871168e+18,
"train_loss": 0.6594652506694975,
"train_runtime": 822.8009,
"train_samples_per_second": 65.629,
"train_steps_per_second": 0.513
} |